GEMs: Breaking the Long-Sequence Barrier in Generative Recommendation with a Multi-Stream Decoder

TL;DR

GEMs introduces a multi-stream decoder framework that effectively captures long-term user interests in generative recommendation systems, overcoming computational and recency bias challenges, and is successfully deployed in industrial settings.

Contribution

The paper proposes GEMs, a novel framework that partitions user behavior sequences into three temporal streams with tailored inference, enabling lifelong modeling and efficient recommendation.

Findings

Outperforms state-of-the-art methods in accuracy on large-scale datasets.

First lifelong generative recommendation framework deployed in industry.

Achieves high inference efficiency with sequences over 100,000 interactions.

Abstract

While generative recommendations (GR) possess strong sequential reasoning capabilities, they face significant challenges when processing extremely long user behavior sequences: the high computational cost forces practical sequence lengths to be limited, preventing models from capturing users' lifelong interests; meanwhile, the inherent "recency bias" of attention mechanisms further weakens learning from long-term history. To overcome this bottleneck, we propose GEMs (Generative rEcommendation with a Multi-stream decoder), a novel and unified framework designed to break the long-sequence barrier by capturing users' lifelong interaction sequences through a multi-stream perspective. Specifically, GEMs partitions user behaviors into three temporal streams$\unicode{x2014}$Recent, Mid-term, and Lifecycle$\unicode{x2014}$and employs tailored inference schemes for each: a one-stage real-time extractor for immediate dynamics, a lightweight indexer for cross attention to balance accuracy and cost for mid-term sequences, and a two-stage offline-online compression module for lifelong modeling. These streams are integrated via a parameter-free fusion strategy to enable holistic interest representation. Extensive experiments on large-scale industrial datasets demonstrate that GEMs significantly outperforms state-of-the-art methods in recommendation accuracy. Notably, GEMs is the first lifelong GR framework successfully deployed in a high-concurrency industrial environment, achieving superior inference efficiency while processing user sequences of over 100,000 interactions.